Latest posts tagged with #OODDetection on Bluesky
SCOPED: Fast Out-of-Distribution Detection for Diffusion Models
SCOPED detects OOD in diffusion models with a single forward pass and a Jacobian‑vector product, matching top precision‑recall while using about one‑tenth the compute. Read more: getnews.me/scoped-fast-out-of-distr... #scoped #ooddetection
SCOPED: Fast Out-of-Distribution Detection for Diffusion Models
SCOPED flags OOD inputs with a single forward pass and one Jacobian‑vector product, cutting passes by about ten‑fold while matching benchmark precision‑recall on four vision datasets. Read more: getnews.me/scoped-fast-out-of-distr... #scoped #ooddetection
Task-Aware OOD Detection Advances Trust in Scientific AI
Task‑aware OOD detection uses a joint likelihood of input and model prediction via a score‑based diffusion model, correlating with error on PDE, satellite and brain‑tumor data. Read more: getnews.me/task-aware-ood-detection... #ooddetection #scientificai
NERO Improves Out-of-Distribution Detection in Medical Imaging
NERO (Neuron-level Relevance for Out-of-Distribution) improves OOD detection in medical imaging, beating state-of-the-art on the Kvasir and GastroVision GI benchmarks (24 Sept 2025). Read more: getnews.me/nero-improves-out-of-dis... #nero #ooddetection
Classification Tasks Influence OOD Detection in Fetal Ultrasound AI
The study evaluated eight methods on ultrasound tasks; image tasks improved OOD detection for lighting shifts, organ‑level tasks helped anatomical shifts. Read more: getnews.me/classification-tasks-inf... #ooddetection #fetalultrasound
Prompt Optimization Meets Subspace Learning for Few-Shot OOD Detection
The framework merges prompt optimization with subspace learning to boost few‑shot OOD detection in vision‑language models, beating prior detectors on real‑world datasets. Read more: getnews.me/prompt-optimization-meet... #ooddetection #vlm
Controlling Neural Collapse Boosts OOD Detection and Transfer Learning
Controlling Neural Collapse boosts OOD detection and transfer‑learning, the study shows. Presented at ICML 2025, it was tested on CIFAR‑10‑C, SVHN and ImageNet‑O. Read more: getnews.me/controlling-neural-colla... #neuralcollapse #ooddetection
Refined Class Learning Improves OOD Detection on Long‑Tailed Data
RSCL adds class‑wise temperature scaling and mines informative outliers, improving OOD detection and tail‑class accuracy versus standard SCL on benchmarks. Read more: getnews.me/refined-class-learning-i... #ooddetection #longtailed
EXPLOR Framework Improves Out-of-Distribution Uncertainty Rejection
Researchers introduced EXPLOR, expanding latent space with pseudo‑labeling to improve OOD uncertainty rejection, achieving accuracy on benchmarks. Read more: getnews.me/explor-framework-improve... #explor #ooddetection #machinelearning
EMOE framework boosts out-of-distribution uncertainty rejection
EMOE (Expansive Matching of Experts) improves OOD rejection with a matching loss, achieving higher accuracy on image, tabular and text benchmarks. Read more: getnews.me/emoe-framework-boosts-ou... #ooddetection #machinelearning
ANTS Method Uses Multimodal LLMs to Boost OOD Detection
ANTS, a training‑free, zero‑shot method using multimodal LLMs, cut the false‑positive rate by 4.2% at 95% recall on ImageNet. The paper was released September 11 2025. Read more: getnews.me/ants-method-uses-multimo... #ants #ooddetection #multimodalllm
🚗✨ How nice would it be to compress robot intelligence without compressing its performance?
📄 Explore the method:
👉 t.co/kB9GcyBUOT
#Robotics #EmbeddedAI #MachineLearning #OODDetection #VAE #AutonomousSystems #JetsonNano t.co/g5TUt5BTRl
